Asr abc - Automatic speech recognition(ASR),中文语音识别

Overview

语音识别的简单示例,主要在课堂演示使用

创建python虚拟环境

在linux 和macos 上验证通过

# 如果已经有pyhon3.6 环境,跳过该步骤,使用现有环境也可以
virtualenv ~/env/asr_abc --python=python3.8
. ~/env/asr_abc/bin/activate

安装本项目

python setup.py install
or 
pip install .

识别wav音频

Note: 输入音频采样率必须是16k,如果待识别音频不是16k,可以采用以下命令重采样为16k.

ffmpeg -i ks1_48k.acc -ar 16000 ks1_16k.wav
python decode.py
# 或debug 模式
python decode.py -d

#预期输出:
2021-12-24 17:08:31,736 INFO [decode.py:91] All files seem exist.
2021-12-24 17:08:31,736 INFO [decode.py:96] Start loading model.
2021-12-24 17:08:41,321 INFO [decode.py:113] Start loading dict.
2021-12-24 17:08:41,336 INFO [decode.py:119] Start recognize data/wavs/BAC009S0764W0143.wav.
2021-12-24 17:08:41,527 INFO [decode.py:134] Result: 在市场整体从高速增长进入中高速增长区间的同时
2021-12-24 17:08:41,527 INFO [decode.py:135] done.

# 也可以指定输入音频
python decode.py --input-wav=data/wavs/ks1_16k.wav
或者
python decode.py -i=data/wavs/ks1_16k.wav  # ks is short for "Kantanzhe Song"
# 预期输出:
2021-12-27 19:16:02,911 INFO [decode.py:91] All files seem exist.
2021-12-27 19:16:02,911 INFO [decode.py:96] Start loading model.
2021-12-27 19:16:08,405 INFO [decode.py:113] Start loading dict.
2021-12-27 19:16:08,409 INFO [decode.py:119] Start recognize data/wavs/ks1_16k.wav.
2021-12-27 19:16:08,449 INFO [decode.py:137] Result: 我们有火焰般的热情
2021-12-27 19:16:08,450 INFO [decode.py:138] done.

相关项目链接:

https://github.com/k2-fsa/icefall
https://github.com/k2-fsa/k2
https://github.com/lhotse-speech/lhotse

手动模型下载

如果上述python decode.py 已识别出预期结果,说明模型已自动从下载源1成功下载模型,无需关注以下内容。

下载源1:(decode.py 代码会自动访问这个源下载): https://huggingface.co/GuoLiyong/cn_conformer_encoder_aishell/tree/main/data/lang_char

下载源2: 百度网盘

链接: https://pan.baidu.com/s/17tPOJM_Sm49q1kZrE3jfUQ
提取码: qa4p

对于访问下载源1有困难或者访问速度过慢的同学,可以手动从百度网盘下载. 下载完毕后按以下文件结构放置下载所得的"tokens.txt"和"conformer_encoder.pt"两个文件:

.
|-- README.md
|-- build
|   `-- bdist.linux-x86_64
|-- conformer.py
|-- data
|   |-- lang_char
|   |   |-- tokens.txt
|   `-- wavs
|       |-- BAC009S0764W0143.wav
|       |-- README.md
|       `-- transcript
|-- decode.py
|-- exp
|   `-- conformer_encoder.pt
|-- requirements.txt
|-- setup.py
`-- utils.py
Owner
LIyong.Guo
LIyong.Guo
The simple project to separate mixed voice (2 clean voices) to 2 separate voices.

Speech Separation The simple project to separate mixed voice (2 clean voices) to 2 separate voices. Result Example (Clisk to hear the voices): mix ||

vuthede 31 Oct 30, 2022
OCR을 이용하여 인원수를 인식 후 줌을 Kill 해줍니다

How To Use killtheZoom-2.0 Windows 0. https://joyhong.tistory.com/79 이 글을 보면서 tesseract를 C:\Program Files\Tesseract-OCR 경로로 설치해주세요(한국어 언어 추가 필요) 상단의 초

김정인 9 Sep 13, 2021
A model library for exploring state-of-the-art deep learning topologies and techniques for optimizing Natural Language Processing neural networks

A Deep Learning NLP/NLU library by Intel® AI Lab Overview | Models | Installation | Examples | Documentation | Tutorials | Contributing NLP Architect

Intel Labs 2.9k Jan 02, 2023
TruthfulQA: Measuring How Models Imitate Human Falsehoods

TruthfulQA: Measuring How Models Imitate Human Falsehoods

69 Dec 25, 2022
🍊 PAUSE (Positive and Annealed Unlabeled Sentence Embedding), accepted by EMNLP'2021 🌴

PAUSE: Positive and Annealed Unlabeled Sentence Embedding Sentence embedding refers to a set of effective and versatile techniques for converting raw

EQT 21 Dec 15, 2022
Russian GPT3 models.

Russian GPT-3 models (ruGPT3XL, ruGPT3Large, ruGPT3Medium, ruGPT3Small) trained with 2048 sequence length with sparse and dense attention blocks. We also provide Russian GPT-2 large model (ruGPT2Larg

Sberbank AI 1.6k Jan 05, 2023
FactSumm: Factual Consistency Scorer for Abstractive Summarization

FactSumm: Factual Consistency Scorer for Abstractive Summarization FactSumm is a toolkit that scores Factualy Consistency for Abstract Summarization W

devfon 83 Jan 09, 2023
BERT, LDA, and TFIDF based keyword extraction in Python

BERT, LDA, and TFIDF based keyword extraction in Python kwx is a toolkit for multilingual keyword extraction based on Google's BERT and Latent Dirichl

Andrew Tavis McAllister 41 Dec 27, 2022
Explore different way to mix speech model(wav2vec2, hubert) and nlp model(BART,T5,GPT) together

SpeechMix Explore different way to mix speech model(wav2vec2, hubert) and nlp model(BART,T5,GPT) together. Introduction For the same input: from datas

Eric Lam 31 Nov 07, 2022
Natural language processing summarizer using 3 state of the art Transformer models: BERT, GPT2, and T5

NLP-Summarizer Natural language processing summarizer using 3 state of the art Transformer models: BERT, GPT2, and T5 This project aimed to provide in

Samuel Sharkey 1 Feb 07, 2022
This repository contains (not all) code from my project on Named Entity Recognition in philosophical text

NERphilosophy 👋 Welcome to the github repository of my BsC thesis. This repository contains (not all) code from my project on Named Entity Recognitio

Ruben 1 Jan 27, 2022
NLP applications using deep learning.

NLP-Natural-Language-Processing NLP applications using deep learning like text generation etc. 1- Poetry Generation: Using a collection of Irish Poem

KASHISH 1 Jan 27, 2022
GrammarTagger — A Neural Multilingual Grammar Profiler for Language Learning

GrammarTagger — A Neural Multilingual Grammar Profiler for Language Learning GrammarTagger is an open-source toolkit for grammatical profiling for lan

Octanove Labs 27 Jan 05, 2023
Concept Modeling: Topic Modeling on Images and Text

Concept is a technique that leverages CLIP and BERTopic-based techniques to perform Concept Modeling on images.

Maarten Grootendorst 120 Dec 27, 2022
AutoGluon: AutoML for Text, Image, and Tabular Data

AutoML for Text, Image, and Tabular Data AutoGluon automates machine learning tasks enabling you to easily achieve strong predictive performance in yo

Amazon Web Services - Labs 5.2k Dec 29, 2022
A multi-voice TTS system trained with an emphasis on quality

TorToiSe Tortoise is a text-to-speech program built with the following priorities: Strong multi-voice capabilities. Highly realistic prosody and inton

James Betker 2.1k Jan 01, 2023
Pattern Matching in Python

Pattern Matching finalmente chega no Python 3.10. E daí? "Pattern matching", ou "correspondência de padrões" como é conhecido no Brasil. Algumas pesso

Fabricio Werneck 6 Feb 16, 2022
A large-scale (194k), Multiple-Choice Question Answering (MCQA) dataset designed to address realworld medical entrance exam questions.

MedMCQA MedMCQA : A Large-scale Multi-Subject Multi-Choice Dataset for Medical domain Question Answering A large-scale, Multiple-Choice Question Answe

MedMCQA 24 Nov 30, 2022
NeMo: a toolkit for conversational AI

NVIDIA NeMo Introduction NeMo is a toolkit for creating Conversational AI applications. NeMo product page. Introductory video. The toolkit comes with

NVIDIA Corporation 5.3k Jan 04, 2023